English

Unconstrained Online Linear Learning in Hilbert Spaces: Minimax Algorithms and Normal Approximations

Machine Learning 2014-05-22 v2

Abstract

We study algorithms for online linear optimization in Hilbert spaces, focusing on the case where the player is unconstrained. We develop a novel characterization of a large class of minimax algorithms, recovering, and even improving, several previous results as immediate corollaries. Moreover, using our tools, we develop an algorithm that provides a regret bound of O(UTlog(UTlog2T+1))\mathcal{O}\Big(U \sqrt{T \log(U \sqrt{T} \log^2 T +1)}\Big), where UU is the L2L_2 norm of an arbitrary comparator and both TT and UU are unknown to the player. This bound is optimal up to loglogT\sqrt{\log \log T} terms. When TT is known, we derive an algorithm with an optimal regret bound (up to constant factors). For both the known and unknown TT case, a Normal approximation to the conditional value of the game proves to be the key analysis tool.

Keywords

Cite

@article{arxiv.1403.0628,
  title  = {Unconstrained Online Linear Learning in Hilbert Spaces: Minimax Algorithms and Normal Approximations},
  author = {H. Brendan McMahan and Francesco Orabona},
  journal= {arXiv preprint arXiv:1403.0628},
  year   = {2014}
}

Comments

Proceedings of the 27th Annual Conference on Learning Theory (COLT 2014)

R2 v1 2026-06-22T03:19:30.223Z